Author

Afsaneh Hasanebrahimi

h-index 1 View on Semantic Scholar

We have 2 of 4 papers

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

Jul 2026

GeoDetect: Geometric Adversarial Detection for VLPs

Theoretical analysis shows that under this anisotropic structure, adversarial attacks increase the expected geometric separation between clean and adversarial examples (AEs), and proposes GeoDetect, which leverages these off-manifold deviations via geometric scores to identify AEs.

Afsaneh Hasanebrahimi, Hanxun Huang, Christopher Leckie et al. · arXiv.org · 0 citations

#machine learning Preprint Aug 2026

VisER: Visual Evidence and Reliance for Object Hallucination Detection in LVLMs

VisER is proposed, a training-free two-sided metric for object-level hallucination detection that improves AUROC and AUPR over a range of baselines and measures whether object-context compatibility is backed by object-specific evidence from image tokens.

Afsaneh Hasanebrahimi, Hanxun Huang, Christopher Leckie et al. · 0 citations